<h1 id="heading-17469">Hitomi Tanaka</h1><h2 id="heading-17470">About</h2>This lora is the second version of my first lora. It can reproduce Hitomi Tanaka, in a realistic way. It will work well with most of the realistic models. To be conform with civitai rules, all pictures and prompts I give are non-suggestive, because it's a real person.To generate sfw pics of her, specify clothes wich will cover her body in your prompt and include (nsfw, cleavage) in the negative prompt.It was trained on a 48 images dataset, various res and size, with captions. The model used was majicmix, 20rep per images, 1000reg images 1024px res, 1rep per reg image, network rank 128, alpha 1, 10 epoch, 19k steps.This is epoch 6 wich i found the best, able to reproduce her while keeping flexibility to change her characteristics like hair color, hair style, clothes etc.<h2 id="heading-17471">How to use</h2>Trigger: hitomi tanaka womanLora weight: 0.7-1Model: realistic one like majicmixcfg: 6-8Resolution: i use 512x768 for first composing, then img2img at 768x1024, denoising: 0.6-0.9 to get final composition.Sampler: Euler A works well, sde karras can produce a "burn effect" at first composition, i use it to rend final composition.Upscale: I use r-esrgan or ldsr and upscale 2x for final images.ControlNet: Can be use but i lower its weight and stop controlling output at 0.15 usually to give some flexibility to the image generation. Only tried canny.Anime Model: i had some good results but lora weight must be set under 0.55 to avoid weird faces.<h2 id="heading-17472">How to get her face right</h2>I do the first composition, then second one, and if i'm unhappy with the face produced, I inpaint and prompt:"hitomi tanaka woman, hitomi tanaka face...(your style)" until I get the right results. You can lower a bit lora weight to get a smoother face.<h2 id="heading-17473">Example of Workflow</h2><h3 id="heading-17474">1) First Composing</h3>model: majicmixsampler: euler aresolution: 512x768batch count: 10steps: 20cfg: 7positive prompt: "hitomi tanaka woman, 1girl, white winter closed wool coat, medium shot, fashion shoot, soft light, best quality, masterpiece, photorealistic, in a snowy forest, RAW photo, &lt;lora:HITOMI_TANAKA-REG-128:1&gt;"negative prompt: "(worst quality:2),(low quality:2),(normal quality:2),lowres,watermark, cleavage, nsfw"Select the one I prefer (only from a composition point of vue), things will be fixed later if needed, send it to img2img<h3 id="heading-17475">2) Refine Composing</h3>img2img tab, this step is the following of step 1model: majicmixsampler: euler aresolution: 768x1024batch count: 5steps: 60denoising: 0.65-0.9 (depending how much i need to alter it)cfg: 7positive prompt: "hitomi tanaka woman, 1girl, white winter closed wool coat, medium shot, fashion shoot, soft light, best quality, masterpiece, photorealistic, in a snowy forest, RAW photo, &lt;lora:HITOMI_TANAKA-REG-128:1&gt;"(adjust lora weight if needed, i go usually from 0.8 to 1)negative prompt: "(worst quality:2),(low quality:2),(normal quality:2),lowres,watermark, cleavage, nsfw"Select the one I prefer<h3 id="heading-17476">3) Inpaint face/other if needed</h3>Mask facedenoising: 0.3-0.75 dependingbatch count: from 1 to 10 dependingpositive prompt: "hitomi tanaka woman, hitomi tanaka face, fashion shoot, soft light, best quality, masterpiece, photorealistic, in a snowy forest, RAW photo, &lt;lora:HITOMI_TANAKA-REG-128:1&gt;"(adjust lora weight if needed, i go usually from 0.8 to 1)negative prompt: "(worst quality:2),(low quality:2),(normal quality:2),lowres,watermark, cleavage, nsfw"<h3 id="heading-17477">4) Finish and Refine</h3>Img2Img, denoising at 0.1-0.3, to get a clean image after inpainting wich can leave some "marks" and strange areas in the pic.Prompts are the one you will find in the text2img tab, the one you use to get your picture wich describe it globally. (or in img2img) if you made some modifications to your prompt at step 2).<h3 id="heading-17478">5) Upscale</h3>Upscaler: R-ESRGAN 4x+ or LDSRResize: 2<h2 id="heading-17479">Final thoughts</h2>I will maybe work on a newer version later, i need to get a more deep understanding of lora training first, and all parameters involved.I'm open to advices, enjoy ;)

Files with SHA256: 416b16ff5b34a460538a0add213c8172f97fc588887aea03b0a668b996e2c60a